SageAttention2 Technical Report: Accurate 4 Bit Attention for Plug-and-play Inference Acceleration
Paper
•
2411.10958
•
Published
•
56
efficient ml
-
-
SpargeAttn: Accurate Sparse Attention Accelerating Any Model Inference
Paper • 2502.18137 • Published • 57 -
SageAttention3: Microscaling FP4 Attention for Inference and An Exploration of 8-Bit Training
Paper • 2505.11594 • Published • 67 -
SageAttention: Accurate 8-Bit Attention for Plug-and-play Inference Acceleration
Paper • 2410.02367 • Published • 51 -
SageAttention2++: A More Efficient Implementation of SageAttention2
Paper • 2505.21136 • Published • 38